Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2024-04-01 (ice)

This series contains updates to ice driver only.

Michal Schmidt changes flow for gettimex64 to use host-side spinlock
rather than hardware semaphore for lighter-weight locking.

Steven adds ability for switch recipes to be re-used when firmware
supports it.

Thorsten Blum removes unwanted newlines in netlink messaging.

Michal Swiatkowski and Piotr re-organize devlink related code; renaming,
moving, and consolidating it to a single location. Michal also
simplifies the devlink init and cleanup path to occur under a single
lock call.

* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  ice: hold devlink lock for whole init/cleanup
  ice: move devlink port code to a separate file
  ice: move ice_devlink.[ch] to devlink folder
  ice: Remove newlines in NL_SET_ERR_MSG_MOD
  ice: Add switch recipe reusing feature
  ice: fold ice_ptp_read_time into ice_ptp_gettimex64
  ice: avoid the PTP hardware semaphore in gettimex64 path
  ice: add ice_adapter for shared data across PFs on the same NIC
====================

Link: https://lore.kernel.org/r/20240401172421.1401696-1-anthony.l.nguyen@intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/intel/ice/Makefile

@@ -5,6 +5,7 @@
 # Makefile for the Intel(R) Ethernet Connection E800 Series Linux Driver
 #
 
+subdir-ccflags-y += -I$(src)
 obj-$(CONFIG_ICE) += ice.o
 
 ice-y := ice_main.o	\
@@ -28,7 +29,8 @@ ice-y := ice_main.o	\
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
 	 ice_idc.o	\
-	 ice_devlink.o	\
+	 devlink/devlink.o	\
+	 devlink/devlink_port.o \
 	 ice_ddp.o	\
 	 ice_fw_update.o \
 	 ice_lag.o	\
@@ -36,7 +38,8 @@ ice-y := ice_main.o	\
 	 ice_repr.o	\
 	 ice_tc_lib.o	\
 	 ice_fwlog.o	\
-	 ice_debugfs.o
+	 ice_debugfs.o  \
+	 ice_adapter.o
 ice-$(CONFIG_PCI_IOV) +=	\
 	ice_sriov.o		\
 	ice_virtchnl.o		\

drivers/net/ethernet/intel/ice/devlink/devlink_port.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024, Intel Corporation. */
+
+#ifndef _DEVLINK_PORT_H_
+#define _DEVLINK_PORT_H_
+
+int ice_devlink_create_pf_port(struct ice_pf *pf);
+void ice_devlink_destroy_pf_port(struct ice_pf *pf);
+int ice_devlink_create_vf_port(struct ice_vf *vf);
+void ice_devlink_destroy_vf_port(struct ice_vf *vf);
+
+#endif /* _DEVLINK_PORT_H_ */

drivers/net/ethernet/intel/ice/ice.h

@@ -77,6 +77,7 @@
 #include "ice_gnss.h"
 #include "ice_irq.h"
 #include "ice_dpll.h"
+#include "ice_adapter.h"
 
 #define ICE_BAR0		0
 #define ICE_REQ_DESC_MULTIPLE	32
@@ -537,6 +538,7 @@ struct ice_agg_node {
 
 struct ice_pf {
 	struct pci_dev *pdev;
+	struct ice_adapter *adapter;
 
 	struct devlink_region *nvm_region;
 	struct devlink_region *sram_region;

drivers/net/ethernet/intel/ice/ice_adapter.c

+// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-FileCopyrightText: Copyright Red Hat
+
+#include <linux/bitfield.h>
+#include <linux/cleanup.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/xarray.h>
+#include "ice_adapter.h"
+
+static DEFINE_XARRAY(ice_adapters);
+
+/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
+#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
+#define INDEX_FIELD_BUS    GENMASK(12, 5)
+#define INDEX_FIELD_SLOT   GENMASK(4, 0)
+
+static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+{
+	unsigned int domain = pci_domain_nr(pdev->bus);
+
+	WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
+
+	return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
+	       FIELD_PREP(INDEX_FIELD_BUS,    pdev->bus->number) |
+	       FIELD_PREP(INDEX_FIELD_SLOT,   PCI_SLOT(pdev->devfn));
+}
+
+static struct ice_adapter *ice_adapter_new(void)
+{
+	struct ice_adapter *adapter;
+
+	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
+	if (!adapter)
+		return NULL;
+
+	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
+	refcount_set(&adapter->refcount, 1);
+
+	return adapter;
+}
+
+static void ice_adapter_free(struct ice_adapter *adapter)
+{
+	kfree(adapter);
+}
+
+DEFINE_FREE(ice_adapter_free, struct ice_adapter*, if (_T) ice_adapter_free(_T))
+
+/**
+ * ice_adapter_get - Get a shared ice_adapter structure.
+ * @pdev: Pointer to the pci_dev whose driver is getting the ice_adapter.
+ *
+ * Gets a pointer to a shared ice_adapter structure. Physical functions (PFs)
+ * of the same multi-function PCI device share one ice_adapter structure.
+ * The ice_adapter is reference-counted. The PF driver must use ice_adapter_put
+ * to release its reference.
+ *
+ * Context: Process, may sleep.
+ * Return:  Pointer to ice_adapter on success.
+ *          ERR_PTR() on error. -ENOMEM is the only possible error.
+ */
+struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+{
+	struct ice_adapter *ret, __free(ice_adapter_free) *adapter = NULL;
+	unsigned long index = ice_adapter_index(pdev);
+
+	adapter = ice_adapter_new();
+	if (!adapter)
+		return ERR_PTR(-ENOMEM);
+
+	xa_lock(&ice_adapters);
+	ret = __xa_cmpxchg(&ice_adapters, index, NULL, adapter, GFP_KERNEL);
+	if (xa_is_err(ret)) {
+		ret = ERR_PTR(xa_err(ret));
+		goto unlock;
+	}
+	if (ret) {
+		refcount_inc(&ret->refcount);
+		goto unlock;
+	}
+	ret = no_free_ptr(adapter);
+unlock:
+	xa_unlock(&ice_adapters);
+	return ret;
+}
+
+/**
+ * ice_adapter_put - Release a reference to the shared ice_adapter structure.
+ * @pdev: Pointer to the pci_dev whose driver is releasing the ice_adapter.
+ *
+ * Releases the reference to ice_adapter previously obtained with
+ * ice_adapter_get.
+ *
+ * Context: Any.
+ */
+void ice_adapter_put(const struct pci_dev *pdev)
+{
+	unsigned long index = ice_adapter_index(pdev);
+	struct ice_adapter *adapter;
+
+	xa_lock(&ice_adapters);
+	adapter = xa_load(&ice_adapters, index);
+	if (WARN_ON(!adapter))
+		goto unlock;
+
+	if (!refcount_dec_and_test(&adapter->refcount))
+		goto unlock;
+
+	WARN_ON(__xa_erase(&ice_adapters, index) != adapter);
+	ice_adapter_free(adapter);
+unlock:
+	xa_unlock(&ice_adapters);
+}

drivers/net/ethernet/intel/ice/ice_adapter.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-FileCopyrightText: Copyright Red Hat */
+
+#ifndef _ICE_ADAPTER_H_
+#define _ICE_ADAPTER_H_
+
+#include <linux/spinlock_types.h>
+#include <linux/refcount_types.h>
+
+struct pci_dev;
+
+/**
+ * struct ice_adapter - PCI adapter resources shared across PFs
+ * @ptp_gltsyn_time_lock: Spinlock protecting access to the GLTSYN_TIME
+ *                        register of the PTP clock.
+ * @refcount: Reference count. struct ice_pf objects hold the references.
+ */
+struct ice_adapter {
+	/* For access to the GLTSYN_TIME register */
+	spinlock_t ptp_gltsyn_time_lock;
+
+	refcount_t refcount;
+};
+
+struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
+void ice_adapter_put(const struct pci_dev *pdev);
+
+#endif /* _ICE_ADAPTER_H */

drivers/net/ethernet/intel/ice/ice_adminq_cmd.h

@@ -264,6 +264,8 @@ struct ice_aqc_set_port_params {
 #define ICE_AQC_RES_TYPE_FLAG_SHARED			BIT(7)
 #define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM		BIT(12)
 #define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX		BIT(13)
+#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED		BIT(14)
+#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL		BIT(15)
 
 #define ICE_AQC_RES_TYPE_FLAG_DEDICATED			0x00
 

drivers/net/ethernet/intel/ice/ice_common.c

@@ -1142,6 +1142,8 @@ int ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
 	mutex_init(&hw->tnl_lock);
+	ice_init_chk_recipe_reuse_support(hw);
+
 	return 0;
 
 err_unroll_fltr_mgmt_struct:

drivers/net/ethernet/intel/ice/ice_dcb_lib.c

@@ -3,7 +3,7 @@
 
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
 
 /**
  * ice_dcb_get_ena_tc - return bitmap of enabled TCs

drivers/net/ethernet/intel/ice/ice_eswitch.c

@@ -7,7 +7,7 @@
 #include "ice_eswitch_br.h"
 #include "ice_fltr.h"
 #include "ice_repr.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
 #include "ice_tc_lib.h"
 
 /**

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -7,7 +7,6 @@
 #include "ice_lib.h"
 #include "ice_fltr.h"
 #include "ice_dcb_lib.h"
-#include "ice_devlink.h"
 #include "ice_vsi_vlan_ops.h"
 
 /**

drivers/net/ethernet/intel/ice/ice_main.c

@@ -13,7 +13,8 @@
 #include "ice_fltr.h"
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
+#include "devlink/devlink_port.h"
 #include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
  * ice tracepoint functions. This must be done exactly once across the
@@ -5093,6 +5094,7 @@ static int
 ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 {
 	struct device *dev = &pdev->dev;
+	struct ice_adapter *adapter;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	int err;
@@ -5145,7 +5147,12 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	pci_set_master(pdev);
 
+	adapter = ice_adapter_get(pdev);
+	if (IS_ERR(adapter))
+		return PTR_ERR(adapter);
+
 	pf->pdev = pdev;
+	pf->adapter = adapter;
 	pci_set_drvdata(pdev, pf);
 	set_bit(ICE_DOWN, pf->state);
 	/* Disable service task until DOWN bit is cleared */
@@ -5179,23 +5186,23 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
-	devl_unlock(priv_to_devlink(pf));
 	if (err)
 		goto err_load;
 
 	err = ice_init_devlink(pf);
 	if (err)
 		goto err_init_devlink;
+	devl_unlock(priv_to_devlink(pf));
 
 	return 0;
 
 err_init_devlink:
-	devl_lock(priv_to_devlink(pf));
 	ice_unload(pf);
-	devl_unlock(priv_to_devlink(pf));
 err_load:
+	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
 err_init:
+	ice_adapter_put(pdev);
 	pci_disable_device(pdev);
 	return err;
 }
@@ -5290,9 +5297,9 @@ static void ice_remove(struct pci_dev *pdev)
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
 
+	devl_lock(priv_to_devlink(pf));
 	ice_deinit_devlink(pf);
 
-	devl_lock(priv_to_devlink(pf));
 	ice_unload(pf);
 	devl_unlock(priv_to_devlink(pf));
 
@@ -5302,6 +5309,7 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_setup_mc_magic_wake(pf);
 	ice_set_wake(pf);
 
+	ice_adapter_put(pdev);
 	pci_disable_device(pdev);
 }
 

drivers/net/ethernet/intel/ice/ice_ptp.c

@@ -374,6 +374,7 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
 	u8 tmr_idx;
 
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
+	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	/* Read the system timestamp pre PHC read */
 	ptp_read_system_prets(sts);
 
@@ -1165,26 +1166,6 @@ static void ice_ptp_reset_cached_phctime(struct ice_pf *pf)
 	ice_ptp_mark_tx_tracker_stale(&pf->ptp.port.tx);
 }
 
-/**
- * ice_ptp_read_time - Read the time from the device
- * @pf: Board private structure
- * @ts: timespec structure to hold the current time value
- * @sts: Optional parameter for holding a pair of system timestamps from
- *       the system clock. Will be ignored if NULL is given.
- *
- * This function reads the source clock registers and stores them in a timespec.
- * However, since the registers are 64 bits of nanoseconds, we must convert the
- * result to a timespec before we can return.
- */
-static void
-ice_ptp_read_time(struct ice_pf *pf, struct timespec64 *ts,
-		  struct ptp_system_timestamp *sts)
-{
-	u64 time_ns = ice_ptp_read_src_clk_reg(pf, sts);
-
-	*ts = ns_to_timespec64(time_ns);
-}
-
 /**
  * ice_ptp_write_init - Set PHC time to provided value
  * @pf: Board private structure
@@ -1925,16 +1906,10 @@ ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts,
 		   struct ptp_system_timestamp *sts)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
-	struct ice_hw *hw = &pf->hw;
-
-	if (!ice_ptp_lock(hw)) {
-		dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n");
-		return -EBUSY;
-	}
-
-	ice_ptp_read_time(pf, ts, sts);
-	ice_ptp_unlock(hw);
+	u64 time_ns;
 
+	time_ns = ice_ptp_read_src_clk_reg(pf, sts);
+	*ts = ns_to_timespec64(time_ns);
 	return 0;
 }
 

drivers/net/ethernet/intel/ice/ice_ptp_hw.c

@@ -274,6 +274,9 @@ void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
  */
 static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
+
+	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
 	ice_flush(hw);
 }

drivers/net/ethernet/intel/ice/ice_repr.c

@@ -3,7 +3,8 @@
 
 #include "ice.h"
 #include "ice_eswitch.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
+#include "devlink/devlink_port.h"
 #include "ice_sriov.h"
 #include "ice_tc_lib.h"
 #include "ice_dcb_lib.h"

drivers/net/ethernet/intel/ice/ice_switch.h

@@ -432,5 +432,6 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
 int
 ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc,
 			     struct ice_sq_cd *cd);
+void ice_init_chk_recipe_reuse_support(struct ice_hw *hw);
 
 #endif /* _ICE_SWITCH_H_ */

drivers/net/ethernet/intel/ice/ice_type.h

@@ -848,6 +848,8 @@ struct ice_hw {
 
 	u16 max_burst_size;	/* driver sets this value */
 
+	u8 recp_reuse:1;	/* indicates whether FW supports recipe reuse */
+
 	/* Tx Scheduler values */
 	u8 num_tx_sched_layers;
 	u8 num_tx_sched_phys_layers;